Neo4j as Graph Memory

Prerequisites

1. Install Mem0 with Graph Memory support

To use Mem0 with Graph Memory support, install it using pip:

pip install "mem0ai[graph]"

This command installs Mem0 along with the necessary dependencies for graph functionality.

2. Install Neo4j

To utilize Neo4j as Graph Memory, run it with Docker:

docker run \
  -p 7474:7474 -p 7687:7687 \
  -e NEO4J_AUTH=neo4j/password \
  neo4j:5

This command starts Neo4j with default credentials (neo4j / password) and exposes both the HTTP (7474) and Bolt (7687) ports.

You can access the Neo4j browser at http://localhost:7474.

Additional information can be found in the Neo4j documentation.

Configuration

Do all the imports and configure OpenAI (enter your OpenAI API key):

In [1]:

from mem0 import Memory

import os

os.environ["OPENAI_API_KEY"] = ""

Set up configuration to use the embedder model and Neo4j as a graph store:

In [2]:

config = {
    "embedder": {
        "provider": "openai",
        "config": {"model": "text-embedding-3-large", "embedding_dims": 1536},
    },
    "graph_store": {
        "provider": "neo4j",
        "config": {
            "url": "bolt://54.87.227.131:7687",
            "username": "neo4j",
            "password": "causes-bins-vines",
        },
    },
}

Graph Memory initializiation

Initialize Neo4j as a Graph Memory store:

In [3]:

m = Memory.from_config(config_dict=config)

Store memories

Create memories:

In [4]:

messages = [
    {
        "role": "user",
        "content": "I'm planning to watch a movie tonight. Any recommendations?",
    },
    {
        "role": "assistant",
        "content": "How about a thriller movies? They can be quite engaging.",
    },
    {
        "role": "user",
        "content": "I'm not a big fan of thriller movies but I love sci-fi movies.",
    },
    {
        "role": "assistant",
        "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future.",
    },
]

Store memories in Neo4j:

In [5]:

# Store inferred memories (default behavior)
result = m.add(messages, user_id="alice")

Search memories

In [6]:

for result in m.search("what does alice love?", user_id="alice")["results"]:
    print(result["memory"], result["score"])

Loves sci-fi movies 0.3153664287340898
Planning to watch a movie tonight 0.09683349296551162
Not a big fan of thriller movies 0.09468540071789466